@huggingface/tasks 0.13.1 → 0.13.2

package/dist/esm/tasks/image-classification/data.js

@@ -0,0 +1,84 @@
+const taskData = {
+    datasets: [
+        {
+            // TODO write proper description
+            description: "Benchmark dataset used for image classification with images that belong to 100 classes.",
+            id: "cifar100",
+        },
+        {
+            // TODO write proper description
+            description: "Dataset consisting of images of garments.",
+            id: "fashion_mnist",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "image-classification-input.jpeg",
+                type: "img",
+            },
+        ],
+        outputs: [
+            {
+                type: "chart",
+                data: [
+                    {
+                        label: "Egyptian cat",
+                        score: 0.514,
+                    },
+                    {
+                        label: "Tabby cat",
+                        score: 0.193,
+                    },
+                    {
+                        label: "Tiger cat",
+                        score: 0.068,
+                    },
+                ],
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "",
+            id: "accuracy",
+        },
+        {
+            description: "",
+            id: "recall",
+        },
+        {
+            description: "",
+            id: "precision",
+        },
+        {
+            description: "",
+            id: "f1",
+        },
+    ],
+    models: [
+        {
+            description: "A strong image classification model.",
+            id: "google/vit-base-patch16-224",
+        },
+        {
+            description: "A robust image classification model.",
+            id: "facebook/deit-base-distilled-patch16-224",
+        },
+        {
+            description: "A strong image classification model.",
+            id: "facebook/convnext-large-224",
+        },
+    ],
+    spaces: [
+        {
+            // TO DO: write description
+            description: "An application that classifies what a given image is about.",
+            id: "nielsr/perceiver-image-classification",
+        },
+    ],
+    summary: "Image classification is the task of assigning a label or class to an entire image. Images are expected to have only one class for each image. Image classification models take an image as input and return a prediction about which class the image belongs to.",
+    widgetModels: ["google/vit-base-patch16-224"],
+    youtubeId: "tjAIM7BOYhw",
+};
+export default taskData;

package/dist/esm/tasks/image-classification/inference.d.ts

@@ -0,0 +1,53 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Image Classification inference
+ */
+export interface ImageClassificationInput {
+    /**
+     * The input image data as a base64-encoded string. If no `parameters` are provided, you can
+     * also provide the image data as a raw bytes payload.
+     */
+    inputs: string;
+    /**
+     * Additional inference parameters
+     */
+    parameters?: ImageClassificationParameters;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters
+ *
+ * Additional inference parameters for Image Classification
+ */
+export interface ImageClassificationParameters {
+    function_to_apply?: ClassificationOutputTransform;
+    /**
+     * When specified, limits the output to the top K most probable classes.
+     */
+    top_k?: number;
+    [property: string]: unknown;
+}
+/**
+ * The function to apply to the model outputs in order to retrieve the scores.
+ */
+export type ClassificationOutputTransform = "sigmoid" | "softmax" | "none";
+export type ImageClassificationOutput = ImageClassificationOutputElement[];
+/**
+ * Outputs of inference for the Image Classification task
+ */
+export interface ImageClassificationOutputElement {
+    /**
+     * The predicted class label.
+     */
+    label: string;
+    /**
+     * The corresponding probability.
+     */
+    score: number;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/image-classification/inference.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-classification/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,wBAAwB;IACxC;;;OAGG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,6BAA6B,CAAC;IAC3C,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;;;GAIG;AACH,MAAM,WAAW,6BAA6B;IAC7C,iBAAiB,CAAC,EAAE,6BAA6B,CAAC;IAClD;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,MAAM,6BAA6B,GAAG,SAAS,GAAG,SAAS,GAAG,MAAM,CAAC;AAC3E,MAAM,MAAM,yBAAyB,GAAG,gCAAgC,EAAE,CAAC;AAC3E;;GAEG;AACH,MAAM,WAAW,gCAAgC;IAChD;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/image-classification/inference.js

@@ -0,0 +1 @@
+export {};

package/dist/esm/tasks/image-feature-extraction/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/image-feature-extraction/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-feature-extraction/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAsDf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/image-feature-extraction/data.js

@@ -0,0 +1,55 @@
+const taskData = {
+    datasets: [
+        {
+            description: "ImageNet-1K is a image classification dataset in which images are used to train image-feature-extraction models.",
+            id: "imagenet-1k",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "mask-generation-input.png",
+                type: "img",
+            },
+        ],
+        outputs: [
+            {
+                table: [
+                    ["Dimension 1", "Dimension 2", "Dimension 3"],
+                    ["0.21236686408519745", "1.0919708013534546", "0.8512550592422485"],
+                    ["0.809657871723175", "-0.18544459342956543", "-0.7851548194885254"],
+                    ["1.3103108406066895", "-0.2479034662246704", "-0.9107287526130676"],
+                    ["1.8536205291748047", "-0.36419737339019775", "0.09717650711536407"],
+                ],
+                type: "tabular",
+            },
+        ],
+    },
+    metrics: [],
+    models: [
+        {
+            description: "A powerful image feature extraction model.",
+            id: "timm/vit_large_patch14_dinov2.lvd142m",
+        },
+        {
+            description: "A strong image feature extraction model.",
+            id: "nvidia/MambaVision-T-1K",
+        },
+        {
+            description: "A robust image feature extraction model.",
+            id: "facebook/dino-vitb16",
+        },
+        {
+            description: "Strong image feature extraction model made for information retrieval from documents.",
+            id: "vidore/colpali",
+        },
+        {
+            description: "Strong image feature extraction model that can be used on images and documents.",
+            id: "OpenGVLab/InternViT-6B-448px-V1-2",
+        },
+    ],
+    spaces: [],
+    summary: "Image feature extraction is the task of extracting features learnt in a computer vision model.",
+    widgetModels: [],
+};
+export default taskData;

package/dist/esm/tasks/image-segmentation/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/image-segmentation/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-segmentation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA8Ff,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/image-segmentation/data.js

@@ -0,0 +1,93 @@
+const taskData = {
+    datasets: [
+        {
+            description: "Scene segmentation dataset.",
+            id: "scene_parse_150",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "image-segmentation-input.jpeg",
+                type: "img",
+            },
+        ],
+        outputs: [
+            {
+                filename: "image-segmentation-output.png",
+                type: "img",
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "Average Precision (AP) is the Area Under the PR Curve (AUC-PR). It is calculated for each semantic class separately",
+            id: "Average Precision",
+        },
+        {
+            description: "Mean Average Precision (mAP) is the overall average of the AP values",
+            id: "Mean Average Precision",
+        },
+        {
+            description: "Intersection over Union (IoU) is the overlap of segmentation masks. Mean IoU is the average of the IoU of all semantic classes",
+            id: "Mean Intersection over Union",
+        },
+        {
+            description: "APα is the Average Precision at the IoU threshold of a α value, for example, AP50 and AP75",
+            id: "APα",
+        },
+    ],
+    models: [
+        {
+            // TO DO: write description
+            description: "Solid semantic segmentation model trained on ADE20k.",
+            id: "openmmlab/upernet-convnext-small",
+        },
+        {
+            description: "Background removal model.",
+            id: "briaai/RMBG-1.4",
+        },
+        {
+            description: "A multipurpose image segmentation model for high resolution images.",
+            id: "ZhengPeng7/BiRefNet",
+        },
+        {
+            description: "Powerful human-centric image segmentation model.",
+            id: "facebook/sapiens-seg-1b",
+        },
+        {
+            description: "Panoptic segmentation model trained on the COCO (common objects) dataset.",
+            id: "facebook/mask2former-swin-large-coco-panoptic",
+        },
+    ],
+    spaces: [
+        {
+            description: "A semantic segmentation application that can predict unseen instances out of the box.",
+            id: "facebook/ov-seg",
+        },
+        {
+            description: "One of the strongest segmentation applications.",
+            id: "jbrinkma/segment-anything",
+        },
+        {
+            description: "A human-centric segmentation model.",
+            id: "facebook/sapiens-pose",
+        },
+        {
+            description: "An instance segmentation application to predict neuronal cell types from microscopy images.",
+            id: "rashmi/sartorius-cell-instance-segmentation",
+        },
+        {
+            description: "An application that segments videos.",
+            id: "ArtGAN/Segment-Anything-Video",
+        },
+        {
+            description: "An panoptic segmentation application built for outdoor environments.",
+            id: "segments/panoptic-segment-anything",
+        },
+    ],
+    summary: "Image Segmentation divides an image into segments where each pixel in the image is mapped to an object. This task has multiple variants such as instance segmentation, panoptic segmentation and semantic segmentation.",
+    widgetModels: ["nvidia/segformer-b0-finetuned-ade-512-512"],
+    youtubeId: "dKE8SIt9C-w",
+};
+export default taskData;

package/dist/esm/tasks/image-segmentation/inference.d.ts

@@ -0,0 +1,70 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Image Segmentation inference
+ */
+export interface ImageSegmentationInput {
+    /**
+     * The input image data as a base64-encoded string. If no `parameters` are provided, you can
+     * also provide the image data as a raw bytes payload.
+     */
+    inputs: string;
+    /**
+     * Additional inference parameters
+     */
+    parameters?: ImageSegmentationParameters;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters
+ *
+ * Additional inference parameters for Image Segmentation
+ */
+export interface ImageSegmentationParameters {
+    /**
+     * Threshold to use when turning the predicted masks into binary values.
+     */
+    mask_threshold?: number;
+    /**
+     * Mask overlap threshold to eliminate small, disconnected segments.
+     */
+    overlap_mask_area_threshold?: number;
+    /**
+     * Segmentation task to be performed, depending on model capabilities.
+     */
+    subtask?: ImageSegmentationSubtask;
+    /**
+     * Probability threshold to filter out predicted masks.
+     */
+    threshold?: number;
+    [property: string]: unknown;
+}
+/**
+ * Segmentation task to be performed, depending on model capabilities.
+ */
+export type ImageSegmentationSubtask = "instance" | "panoptic" | "semantic";
+export type ImageSegmentationOutput = ImageSegmentationOutputElement[];
+/**
+ * Outputs of inference for the Image Segmentation task
+ *
+ * A predicted mask / segment
+ */
+export interface ImageSegmentationOutputElement {
+    /**
+     * The label of the predicted segment.
+     */
+    label: string;
+    /**
+     * The corresponding mask as a black-and-white image (base64-encoded).
+     */
+    mask: string;
+    /**
+     * The score or confidence degree the model has.
+     */
+    score?: number;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/image-segmentation/inference.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-segmentation/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,sBAAsB;IACtC;;;OAGG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,2BAA2B,CAAC;IACzC,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;;;GAIG;AACH,MAAM,WAAW,2BAA2B;IAC3C;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,2BAA2B,CAAC,EAAE,MAAM,CAAC;IACrC;;OAEG;IACH,OAAO,CAAC,EAAE,wBAAwB,CAAC;IACnC;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,MAAM,wBAAwB,GAAG,UAAU,GAAG,UAAU,GAAG,UAAU,CAAC;AAC5E,MAAM,MAAM,uBAAuB,GAAG,8BAA8B,EAAE,CAAC;AACvE;;;;GAIG;AACH,MAAM,WAAW,8BAA8B;IAC9C;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/image-segmentation/inference.js

@@ -0,0 +1 @@
+export {};

package/dist/esm/tasks/image-text-to-text/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/image-text-to-text/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-text-to-text/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAiGf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/image-text-to-text/data.js

@@ -0,0 +1,97 @@
+const taskData = {
+    datasets: [
+        {
+            description: "Instructions composed of image and text.",
+            id: "liuhaotian/LLaVA-Instruct-150K",
+        },
+        {
+            description: "Conversation turns where questions involve image and text.",
+            id: "liuhaotian/LLaVA-Pretrain",
+        },
+        {
+            description: "A collection of datasets made for model fine-tuning.",
+            id: "HuggingFaceM4/the_cauldron",
+        },
+        {
+            description: "Screenshots of websites with their HTML/CSS codes.",
+            id: "HuggingFaceM4/WebSight",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "image-text-to-text-input.png",
+                type: "img",
+            },
+            {
+                label: "Text Prompt",
+                content: "Describe the position of the bee in detail.",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                label: "Answer",
+                content: "The bee is sitting on a pink flower, surrounded by other flowers. The bee is positioned in the center of the flower, with its head and front legs sticking out.",
+                type: "text",
+            },
+        ],
+    },
+    metrics: [],
+    models: [
+        {
+            description: "Powerful vision language model with great visual understanding and reasoning capabilities.",
+            id: "meta-llama/Llama-3.2-11B-Vision-Instruct",
+        },
+        {
+            description: "Cutting-edge vision language models.",
+            id: "allenai/Molmo-7B-D-0924",
+        },
+        {
+            description: "Small yet powerful model.",
+            id: "vikhyatk/moondream2",
+        },
+        {
+            description: "Strong image-text-to-text model.",
+            id: "Qwen/Qwen2-VL-7B-Instruct",
+        },
+        {
+            description: "Strong image-text-to-text model.",
+            id: "mistralai/Pixtral-12B-2409",
+        },
+        {
+            description: "Strong image-text-to-text model focused on documents.",
+            id: "stepfun-ai/GOT-OCR2_0",
+        },
+    ],
+    spaces: [
+        {
+            description: "Leaderboard to evaluate vision language models.",
+            id: "opencompass/open_vlm_leaderboard",
+        },
+        {
+            description: "Vision language models arena, where models are ranked by votes of users.",
+            id: "WildVision/vision-arena",
+        },
+        {
+            description: "Powerful vision-language model assistant.",
+            id: "akhaliq/Molmo-7B-D-0924",
+        },
+        {
+            description: "An image-text-to-text application focused on documents.",
+            id: "stepfun-ai/GOT_official_online_demo",
+        },
+        {
+            description: "An application to compare outputs of different vision language models.",
+            id: "merve/compare_VLMs",
+        },
+        {
+            description: "An application for chatting with an image-text-to-text model.",
+            id: "GanymedeNil/Qwen2-VL-7B",
+        },
+    ],
+    summary: "Image-text-to-text models take in an image and text prompt and output text. These models are also called vision-language models, or VLMs. The difference from image-to-text models is that these models take an additional text input, not restricting the model to certain use cases like image captioning, and may also be trained to accept a conversation as input.",
+    widgetModels: ["meta-llama/Llama-3.2-11B-Vision-Instruct"],
+    youtubeId: "IoGaGfU1CIg",
+};
+export default taskData;

package/dist/esm/tasks/image-to-3d/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/image-to-3d/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-to-3d/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAsEf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/image-to-3d/data.js

@@ -0,0 +1,72 @@
+const taskData = {
+    datasets: [
+        {
+            description: "A large dataset of over 10 million 3D objects.",
+            id: "allenai/objaverse-xl",
+        },
+        {
+            description: "A dataset of isolated object images for evaluating image-to-3D models.",
+            id: "dylanebert/iso3d",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "image-to-3d-image-input.png",
+                type: "img",
+            },
+        ],
+        outputs: [
+            {
+                label: "Result",
+                content: "image-to-3d-3d-output-filename.glb",
+                type: "text",
+            },
+        ],
+    },
+    metrics: [],
+    models: [
+        {
+            description: "Fast image-to-3D mesh model by Tencent.",
+            id: "TencentARC/InstantMesh",
+        },
+        {
+            description: "Fast image-to-3D mesh model by StabilityAI",
+            id: "stabilityai/TripoSR",
+        },
+        {
+            description: "A scaled up image-to-3D mesh model derived from TripoSR.",
+            id: "hwjiang/Real3D",
+        },
+        {
+            description: "Generative 3D gaussian splatting model.",
+            id: "ashawkey/LGM",
+        },
+    ],
+    spaces: [
+        {
+            description: "Leaderboard to evaluate image-to-3D models.",
+            id: "dylanebert/3d-arena",
+        },
+        {
+            description: "Image-to-3D demo with mesh outputs.",
+            id: "TencentARC/InstantMesh",
+        },
+        {
+            description: "Image-to-3D demo with mesh outputs.",
+            id: "stabilityai/TripoSR",
+        },
+        {
+            description: "Image-to-3D demo with mesh outputs.",
+            id: "hwjiang/Real3D",
+        },
+        {
+            description: "Image-to-3D demo with splat outputs.",
+            id: "dylanebert/LGM-mini",
+        },
+    ],
+    summary: "Image-to-3D models take in image input and produce 3D output.",
+    widgetModels: [],
+    youtubeId: "",
+};
+export default taskData;

package/dist/esm/tasks/image-to-image/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/image-to-image/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-to-image/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAgGf,CAAC;AAEF,eAAe,QAAQ,CAAC"}